© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 100166
    Prev
    Next
    INDEX
    Explanations

    Откуда взялся

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    蟶
    -3.36
    Ꮠ
    -3.08
    ሷ
    -2.98
     唯美
    -2.88
    橚
    -2.81
    鱨
    -2.80
     camiset
    -2.77
    獁
    -2.75
     手绘
    -2.73
     blik
    -2.73
    POSITIVE LOGITS
     are
    3.86
     They
    3.38
     diversos
    3.20
    </em>
    2.91
    みたら
    2.67
    見ると
    2.61
    </h4>
    2.52
     Their
    2.52
    癀
    2.50
    みると
    2.47
    Activations Density 0.000%

    No Known Activations